CN112464990B - Method and device for sensing vibration data based on current-voltage sensor - Google Patents
Method and device for sensing vibration data based on current-voltage sensor Download PDFInfo
- Publication number
- CN112464990B CN112464990B CN202011212653.8A CN202011212653A CN112464990B CN 112464990 B CN112464990 B CN 112464990B CN 202011212653 A CN202011212653 A CN 202011212653A CN 112464990 B CN112464990 B CN 112464990B
- Authority
- CN
- China
- Prior art keywords
- network
- data
- current
- sample data
- vibration
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000012549 training Methods 0.000 claims abstract description 87
- 238000006243 chemical reaction Methods 0.000 claims abstract description 24
- 230000006870 function Effects 0.000 claims description 24
- 238000005070 sampling Methods 0.000 claims description 17
- 238000013527 convolutional neural network Methods 0.000 claims description 13
- 238000013075 data extraction Methods 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 abstract description 13
- 238000004364 calculation method Methods 0.000 abstract description 8
- 230000008485 antagonism Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 8
- 230000001133 acceleration Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Probability & Statistics with Applications (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The embodiment of the invention provides a method and a device for sensing vibration data based on a current-voltage sensor, wherein the method comprises the following steps: acquiring current and voltage data acquired by a current and voltage sensor; inputting the current and voltage data into a generator network to obtain virtual vibration data; the system comprises a generator network, a discriminator network, a first training set and a second training set, wherein the generator network and the discriminator network form an countermeasure network, and the countermeasure network is obtained by training a first training set through pre-collected current and voltage sample data, real vibration sample data corresponding to the current and voltage sample data and fault types corresponding to the current and voltage sample data. According to the method provided by the embodiment of the invention, the antagonism training is carried out by combining the generator network and the discriminator network into the antagonism network, so that the calculation capability of the generator network to the data is gradually improved, a better data conversion process can be realized under the condition of ensuring the implicit state characteristics of the data, and the virtual sensing function from the current and voltage data to the virtual vibration data of the generator network is realized.
Description
Technical Field
The present invention relates to the field of virtual sensing technologies, and in particular, to a method and apparatus for sensing vibration data based on a current-voltage sensor, an electronic device, and a storage medium.
Background
Although the sensors are intelligent and integrated to gradually form ubiquitous sensing at present, most of the detected objects have complex structures, and the sensors are difficult to arrange in the inside or on the surface side of the detected objects, or the operations of selecting, installing, wiring, maintaining and the like of the sensors are extremely time-consuming and labor-consuming, and the operation cost of the equipment is greatly increased.
In general, most devices can be equipped with current and voltage sensors at the time of shipment, or the steps of adding current and voltage sensors are relatively simple. Therefore, the intelligent sensing and judging of the state of the motor equipment are realized by calculating the vibration data of the equipment from the sensor data such as current, voltage and the like, so that the virtual sensing is formed as an effective equipment state sensing scheme.
In the prior art, although a virtual sensing scheme tries to adopt a regression algorithm such as machine learning to perform a mapping process from current and voltage data to vibration data, mathematical errors between the converted data and standard data are small, and the converted data basically lose the health state characteristics of equipment contained in the vibration data, so that the schemes are difficult to adapt to actual application demands.
Therefore, how to propose a method to complete the conversion from the current voltage data to the vibration data of the device without losing the hidden state characteristics of the device, thereby forming a virtual sensing process, and becoming a problem to be solved.
Disclosure of Invention
The embodiment of the invention provides a method and a device for sensing vibration data based on a current-voltage sensor, electronic equipment and a storage medium, which are used for solving the technical defects in the prior art.
The embodiment of the invention provides a method for sensing vibration data based on a current-voltage sensor, which comprises the following steps:
Acquiring current and voltage data acquired by a current and voltage sensor;
Inputting the current and voltage data into a generator network to obtain virtual vibration data;
The system comprises a generator network, a discriminator network, a first training set and a second training set, wherein the generator network and the discriminator network form an countermeasure network, and the countermeasure network is obtained by training a first training set through pre-collected current and voltage sample data, real vibration sample data corresponding to the current and voltage sample data and fault types corresponding to the current and voltage sample data.
According to a method of sensing vibration data based on a current-voltage sensor according to one embodiment of the present invention, the generator network comprises: a downsampling layer, a data conversion layer and an upsampling layer;
inputting the current voltage data into a generator network to obtain virtual vibration data, comprising:
the downsampling layer receives input current and voltage data and generates first sampling data;
the data conversion layer receives input first sampling data and generates first conversion data;
the up-sampling layer receives the input first conversion data and generates virtual vibration data.
According to a method for sensing vibration data based on a current-voltage sensor according to one embodiment of the present invention, the countermeasure network is trained by:
The current and voltage sample data and the real vibration sample data corresponding to the current and voltage sample data form a second training set to be input into the generator network so as to train the generator network;
Marking the vibration data output by the generator network as virtual vibration sample data, and inputting a third training set composed of the virtual vibration sample data, the real vibration sample data corresponding to the virtual vibration sample data and the fault type thereof into the discriminator network to train the discriminator network;
And forming the obtained generator network and the obtained discriminator network into an countermeasure network, and inputting the first training set into the countermeasure network to train the countermeasure network.
According to one embodiment of the invention, a method for sensing vibration data based on a current-voltage sensor, the discriminator network comprises a first discriminator network and a second discriminator network;
The virtual vibration sample data, the real vibration sample data corresponding to the virtual vibration sample data and the fault type thereof form a third training set to be input into the discriminator network so as to train the discriminator network, and the method comprises the following steps:
inputting the virtual vibration sample data and the real vibration sample data to a first arbiter network to train the first arbiter network;
And inputting virtual vibration sample data, the real vibration sample data and the fault type thereof into a second discriminator network to train the second discriminator network.
According to a method for sensing vibration data based on a current-voltage sensor according to an embodiment of the present invention, the resulting generator network and the arbiter network form an countermeasure network, the first training set is input to the countermeasure network to train the countermeasure network, including:
Inputting the first training set into the countermeasure network, and alternately locking parameters of the discriminator network or the generator network to update the parameters of the generator network or the discriminator network so that a loss function of the countermeasure network is smaller than a first threshold, wherein the loss function of the countermeasure network is a combination of the loss functions of the first discriminator network and the second discriminator network.
According to the method for sensing vibration data based on the current-voltage sensor, the first discriminator network is a convolutional neural network;
Inputting the virtual vibration sample data and the real vibration sample data to a first arbiter network to train the first arbiter network, comprising:
Inputting the virtual vibration sample data and the real vibration sample data into a first discriminator network to obtain the probability that the currently input data is the real vibration sample data;
and adjusting parameters of the first discriminator network so that the probability is greater than a second threshold when the input data is real vibration sample data.
According to a method of sensing vibration data based on a current-voltage sensor according to one embodiment of the present invention, the second discriminator network comprises: a first convolution layer, a time sequence data extraction layer, a second convolution layer and a normalization layer;
Inputting the virtual vibration sample data, the real vibration sample data and the fault type thereof into a second discriminator network to train the second discriminator network, comprising:
inputting the real vibration sample data and the virtual vibration sample data into a first convolution layer to generate first convolution data;
inputting the first convolution data to a time sequence data extraction layer to generate time sequence data;
inputting the time sequence data into the second convolution layer to generate second convolution data;
Inputting the second convolution data to a normalization layer to generate the prediction probability of the fault type of the real vibration sample data;
inputting the fault type of the real vibration sample data, comparing the prediction probability with the fault type of the real vibration sample data, and counting the prediction accuracy of a second discriminator;
And adjusting parameters of the second discriminator network with the aim of the prediction accuracy being larger than a third threshold.
The embodiment of the invention also provides a device for sensing vibration data based on the current-voltage sensor, which is characterized by comprising:
the acquisition module is used for acquiring current and voltage data acquired by the current and voltage sensor;
the sensing module is used for inputting the current and voltage data into the generator network so as to obtain virtual vibration data;
The system comprises a generator network, a discriminator network, a first training set and a second training set, wherein the generator network and the discriminator network form an countermeasure network, and the countermeasure network is obtained by training a first training set through pre-collected current and voltage sample data, real vibration sample data corresponding to the current and voltage sample data and fault types corresponding to the current and voltage sample data.
The embodiment of the invention also provides electronic equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the steps of the method for sensing vibration data based on the current-voltage sensor when executing the program.
Embodiments of the present invention also provide a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of a method of sensing vibration data based on a current-voltage sensor as described in any of the above.
According to the method and the device for sensing vibration data based on the current and voltage sensor, provided by the embodiment of the invention, the calculation capability of the generator network to the data is gradually improved by forming the counter network from the generator network and the discriminator network to perform counter training, so that a better data conversion process can be realized under the condition of ensuring the implicit state characteristics of the data, and the virtual sensing function from the current and voltage data to the virtual vibration data of the generator network is realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for sensing vibration data based on a current-voltage sensor according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a generator network provided by an embodiment of the present invention;
FIG. 3 is a flow chart of a training process of an countermeasure network according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a second training set provided by an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a second identifier network according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of an apparatus for sensing vibration data based on a current-voltage sensor according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terminology used in the one or more embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the one or more embodiments of the invention. As used in one or more embodiments of the invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used in one or more embodiments of the present invention refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that, although the terms first, second, etc. may be used in one or more embodiments of the invention to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first may also be referred to as a second, and similarly, a second may also be referred to as a first, without departing from the scope of one or more embodiments of the invention. The word "if" as used herein may be interpreted as "at … …" or "at … …" or "in response to a determination" depending on the context.
The embodiment of the invention provides a method for sensing vibration data based on a current-voltage sensor, which is shown in fig. 1 and comprises the following steps:
101. and acquiring current and voltage data acquired by the current and voltage sensor.
The current and voltage sensor is arranged on the target equipment, and after the motor of the target equipment is started to enable the target equipment to operate, current and voltage sensor data of the target equipment operating in different states are collected.
102. The current voltage data is input into the generator network to obtain virtual vibration data.
Specifically, referring to fig. 2, fig. 2 shows a structure of a generator network according to an embodiment of the present invention, where the generator network includes: a downsampling layer, a data conversion layer and an upsampling layer.
Step 102 includes the following steps S121 to S123:
S121, receiving input current and voltage data by a downsampling layer to generate first sampling data;
S122, the data conversion layer receives input first sampling data and generates first conversion data;
s123, the up-sampling layer receives the input first conversion data and generates virtual vibration data.
Since LSTM networks are relatively adept at processing time-series data, unlike conventional countermeasure networks, the present invention proposes a basic network framework that uses LSTM networks instead of CNN networks as generators. In this embodiment, the downsampling layer uses a CNN network, the data conversion layer uses an LSTM network, and the upsampling layer uses a CNN network.
In this embodiment, the sensing data is converted for 1 second each time, and the sampling rate of the sensing data is 2000 times per second, so that the generator needs to input and output 2000-dimensional time sequence data per second, and each-dimensional input data comprises five data such as three-phase current and two-phase voltage at the current moment, and each-dimensional output data comprises three data such as three-axis vibration acceleration at the current moment. For LSTM network, 2000 length data is too huge, because as the length of time sequence data is increased, the number of times of reverse calculation of the neural network is increased, so that the problem of gradient explosion or gradient disappearance is caused, and finally, the updating process of parameters in the network is limited, so that the relevance of front and rear data is disappeared, and the processing performance of the network on ultra-long time sequence is limited. Therefore, the length of the LSTM network adopted in this embodiment is 128 dimensions, the input data of each dimension is composed of 5 values, the output is 3 data, meanwhile, a CNN downsampling layer is added in front of the LSTM network, and a CNN upsampling layer is added behind the LSTM network. The CNN downsampling layer consists of several convolution layers and downsampling layers for reducing 2000-dimensional input data to 128-dimensional to reduce the length required by the LSTM network. The CNN up-sampling layer consists of a plurality of convolution layers and an up-sampling layer and is used for restoring the 128-dimensional output data to 2000-dimensional, so that the format of the vibration acceleration data output by the generator network is consistent with that of the real vibration acceleration data.
According to the embodiment of the invention, the generator network with the CNN-LSTM-CNN structure is constructed, so that the network structure is simple and easy to construct. The CNN network is used for carrying out the dimension reduction and dimension increase operation of the data, so that the time sequence data can be better perceived and processed by the LSTM network, and meanwhile, the format of the finally output data consistent with the original data can be ensured, and the data conversion process can be carried out stably.
In addition, it should be noted that, in this embodiment, the countermeasure network is trained by forming the generator network and the arbiter network into the countermeasure network, so as to improve the calculation capability of the generator network for data. The countermeasure network is trained by forming a first training set through pre-collected current and voltage sample data, real vibration sample data and fault types corresponding to the current and voltage sample data.
According to the method for sensing vibration data based on the current and voltage sensor, provided by the embodiment of the invention, the antagonism training is carried out by combining the generator network and the discriminator network to gradually improve the calculation capability of the generator network to the data, so that a better data conversion process can be realized under the condition of ensuring the implicit state characteristics of the data, and the virtual sensing function from the current and voltage data to the virtual vibration data of the generator network is realized.
The training process of the countermeasure network according to the present embodiment is explained in detail below. Referring to fig. 3, the training steps of the countermeasure network include 301 to 303:
301. And inputting the current and voltage sample data and the real vibration sample data corresponding to the current and voltage sample data into the generator network to train the generator network.
The second training set is a current-voltage sensor and a vibration acceleration sensor which are arranged for the equipment, then the motor is started, and sensor data of the equipment in different states and running for a certain time are collected and stored according to a specified format.
Fig. 4 is a schematic diagram of a second training set. As can be seen in the figure, the acquired data includes: sampling time sequence, one-phase voltage, two-phase voltage, three-phase voltage, one-phase current, two-phase current, x-axis vibration acceleration, y-axis vibration acceleration and z-axis vibration acceleration.
In addition, the embodiment also collects data under 9 motor working conditions (normal, A1 rotor imbalance (outer ring), A2 rotor imbalance (outer ring), A1B1 rotor imbalance (outer ring), inner ring failure, outer ring failure, ball mild, ball moderate, ball severe). Wherein, 6 groups of data are collected under each working condition, each group is 5 minutes, and the sampling rate is 2000 times per second. All data were as per 8: and 2, setting a training/testing set in proportion for training and optimizing an algorithm model.
The generator network model is trained to convert the current voltage data into virtual vibration data that is substantially similar to the real vibration data. At this time, one second of sensor data is taken as one sample, with the current-voltage sample data as the input sample, and the network calculates 2000-dimensional output data, i.e., virtual vibration sample data, from the input. And after the network calculation is finished, calculating errors of the real vibration data and the virtual vibration sample data by using the corresponding real vibration data as a label, and reversely updating weight parameters of each part of the generator network with the aim of minimizing the errors. The mean square error loss function is used for calculating the error, and the formula is shown in the following formula (1):
Where MSE represents the value of the loss function and n is the number of samples used in a training process. y i ′ represents the value calculated by the network from the current lot i sample, and y i represents the actual vibration data, i.e., the label, of the current lot i sample.
302. And marking the vibration data output by the generator network as virtual vibration sample data, and inputting the virtual vibration sample data, the real vibration sample data corresponding to the virtual vibration sample data and the fault type thereof into the discriminator network to train the discriminator network.
In this embodiment, step 302 includes:
S321, inputting the virtual vibration sample data and the real vibration sample data into a first discriminator network to train the first discriminator network.
S322, inputting the virtual vibration sample data, the real vibration sample data and the fault type thereof into a second discriminator network to train the second discriminator network.
In particular, the virtual sensor data should be sufficiently close to the real vibration data, and furthermore, should have the availability of real data, for example, can be used in situations such as state monitoring, fault classification, equipment health assessment, etc. Therefore, the embodiment of the invention proposes an countermeasure network using a multi-arbiter single generator structure, and virtual data can cover more application scenes by increasing the types of the arbiters. For example, in the present embodiment, it is proposed to use a true-false data classification network and a fault classification network as a first discriminator network and a second discriminator network, respectively, the second discriminator network being as shown in fig. 5.
The first arbiter network is used to evaluate whether the received data is authentic or given by the generator. In this embodiment, the first arbiter network is a CNN-type neural network, and is composed of a plurality of convolution layers, a downsampling layer, a full connection layer, and a softmax classifier.
During training, generating 2000-dimensional vectors from virtual vibration sample data and real vibration sample data, and inputting the vectors to a first discriminator network to obtain the probability that the current input data is the real vibration sample data, wherein the probability value is 0 to 1; the parameters of the first arbiter network are adjusted such that the probability is greater than a second threshold when the input data is true vibration sample data.
For the second discriminator network, the data output by the generator tends to realize the function of fault classification, so that virtual data is ensured to be not only in the form of real data, but also have the capability of detecting equipment faults. Specifically, the second discriminator includes: a first convolution layer, a time sequence data extraction layer, a second convolution layer and a normalization layer. In order to achieve better time sequence data processing performance, the second discriminator adopts an LSTM network as a time sequence data extraction layer, and the first convolution layer and the second convolution layer both adopt CNN network layers.
During training, the method comprises the following steps: inputting the real vibration sample data or the virtual vibration sample data into the first convolution layer to generate first convolution data; inputting the first convolution data to a time sequence data extraction layer to generate time sequence data; inputting the time sequence data into the second convolution layer to generate second convolution data; inputting the second convolution data to the normalization layer to generate the prediction probability of the fault type of the real vibration sample data; inputting the fault type of the real vibration sample data, comparing the prediction probability with the fault type of the real vibration sample data, and counting the prediction accuracy of a second discriminator; and adjusting parameters of the second discriminator network by taking the prediction accuracy larger than a third threshold as a target.
Specifically, the first convolution layer is used for reducing the data from 2000 dimensions to 128 dimensions, then the LSTM time sequence data extraction layer is used for extracting the time sequence characteristics of the data, then the time sequence data is input into the second convolution layer for further reducing the dimension to 10 dimensions, and finally the second convolution data is input into the softmax normalization layer, so that the accuracy of the prediction fault type to which the data belongs is estimated. The specific fault types include the 9 types described above, plus a "virtual data" class, totaling 10 classes.
In this embodiment, the purpose of the training is to enable the first discriminator to distinguish between real vibration data and virtual vibration data, and enable the second discriminator to distinguish between the types of faults represented by the real vibration data, or whether the input data is virtual vibration data or real vibration data. Since both finally use the softmax function to give a type decision, both use the cross entropy loss function, as shown in equation (2) below:
Wherein L represents the value of the loss function;
n is the number of samples used in one training process;
M is the total number of all data types, for a first arbiter network, the value of M is 2, for a second arbiter network, the value of M is 10;
y ic represents the true type of the nth sample data, and if the c type is the c type, the value is 1, otherwise, the value is 0;
p ic represents the probability that the n-th sample data is considered to be class c data after evaluation by the arbiter network.
303. And forming the obtained generator network and the obtained discriminator network into an countermeasure network, and inputting the first training set into the countermeasure network to train the countermeasure network.
Specifically, step 303 includes: inputting the first training set into the countermeasure network, and alternately locking parameters of the discriminator network or the generator network to update the parameters of the generator network or the discriminator network so that the loss function of the countermeasure network is smaller than a first threshold, wherein the loss function of the countermeasure network is a loss function combination of the first discriminator network and the second discriminator network.
The loss function formula of the countermeasure network is shown in the following formula (3):
Wherein, N is the number of samples used in one training process, L A、LB is the loss values of the first and second discriminator networks, a and b are the weighting parameters of the loss values of the first and second discriminator networks, and the generator network is stressed to different conversion targets by adjusting the values of a and b.
Specifically, the weight value of the discriminator network is locked first, then virtual vibration data is generated according to the voltage and current data of the sample by using the generator network, the predicted value of the type of the virtual data is given by using the discriminator network, and the weight value of the generator network is adjusted according to the predicted deviation. At this time, the targets of the weight update are: (1) The first discriminator evaluates the virtual vibration sample data as real vibration sample data as far as possible; (2) The second discriminator is made to coincide the fault prediction type of the virtual vibration sample data with the fault type to which the real current voltage data belongs as much as possible. Thus, for a certain virtual vibration sample data, its label changes from 0 to 1 for the first arbiter; for the second discriminator, its label changes from "virtual data class" to "failure class corresponding to real vibration sample data".
And then locking the weight value of the generator network, and training the discriminator network, wherein the training target is consistent with the training target in the step 302, namely the loss function of the countermeasure network is smaller than a first threshold.
Through multiple iterations, the generator network and the arbiter network performance are greatly improved. And finally, independently taking out the generator network, namely, a network model capable of carrying out virtual vibration data calculation based on current and voltage, and packaging the network model into a model for application and deployment.
The embodiment of the invention uses the countermeasure network structure of the single generator network-multi-discriminant network, and realizes the functional effectiveness of the generator network generated data by adding the discriminant network with multiple types of functions, for example, the fault classification is used as an evaluation discriminator, so that the virtual vibration data and the real vibration data can be ensured to have small numerical errors and the fault identification performance. By setting the weight of the discriminator network, different functional emphasis of the virtual data is realized respectively.
Based on any of the above embodiments, fig. 6 is a schematic structural diagram of an apparatus for sensing vibration data based on a current-voltage sensor according to an embodiment of the present invention, as shown in fig. 6, including:
An acquisition module 601, configured to acquire current voltage data acquired by a current voltage sensor;
The sensing module 602 is configured to input current and voltage data into the generator network to obtain virtual vibration data;
The system comprises a generator network, a discriminator network, a first training set and a second training set, wherein the generator network and the discriminator network form an countermeasure network, and the countermeasure network is obtained by training a first training set through pre-collected current and voltage sample data, real vibration sample data corresponding to the current and voltage sample data and fault types corresponding to the current and voltage sample data.
Optionally, the generator network comprises: a downsampling layer, a data conversion layer and an upsampling layer;
the sensing module 602 is specifically configured to:
the downsampling layer receives input current and voltage data and generates first sampling data;
the data conversion layer receives input first sampling data and generates first conversion data;
the up-sampling layer receives the input first conversion data and generates virtual vibration data.
Optionally, the device for sensing vibration data based on the current-voltage sensor further comprises:
The first training module is used for forming a second training set from the current and voltage sample data and the real vibration sample data corresponding to the current and voltage sample data and inputting the second training set into the generator network so as to train the generator network;
The second training module is used for marking the vibration data output by the generator network as virtual vibration sample data, and forming a third training set by the virtual vibration sample data, the real vibration sample data corresponding to the virtual vibration sample data and the fault type thereof to be input into the discriminator network so as to train the discriminator network;
And the third training module is used for forming the obtained generator network and the obtained discriminator network into an countermeasure network, and inputting the first training set into the countermeasure network so as to train the countermeasure network.
Optionally, the arbiter network comprises a first arbiter network and a second arbiter network;
the second training module is specifically configured to:
inputting the virtual vibration sample data and the real vibration sample data to a first arbiter network to train the first arbiter network;
And inputting the virtual vibration sample data, the real vibration sample data and the fault type thereof into a second discriminator network to train the second discriminator network.
Optionally, the third training module is specifically configured to: inputting the first training set into the countermeasure network, and alternately locking parameters of the discriminator network or the generator network to update the parameters of the generator network or the discriminator network so that a loss function of the countermeasure network is smaller than a first threshold, wherein the loss function of the countermeasure network is a combination of the loss functions of the first discriminator network and the second discriminator network.
Optionally, the first arbiter network is a convolutional neural network;
the second training module is specifically configured to:
inputting the virtual vibration sample data and the real vibration sample data into a first discriminator network to obtain the probability that the currently input data is the real vibration sample data;
and adjusting parameters of the first discriminator network so that the probability is greater than a second threshold when the input data is real vibration sample data.
Optionally, the second arbiter network comprises: a first convolution layer, a time sequence data extraction layer, a second convolution layer and a normalization layer;
the second training module is specifically configured to:
inputting the real vibration sample data and the virtual vibration sample data into a first convolution layer to generate first convolution data;
inputting the first convolution data to a time sequence data extraction layer to generate time sequence data;
inputting the time sequence data into the second convolution layer to generate second convolution data;
Inputting the second convolution data to a normalization layer to generate the prediction probability of the fault type of the real vibration sample data;
Inputting the fault type of the real vibration sample data, comparing the prediction probability with the fault type of the real vibration sample data, and counting the prediction accuracy of a second discriminator;
and adjusting parameters of the second discriminator network by taking the prediction accuracy larger than a third threshold as a target.
According to the device for sensing vibration data based on the current and voltage sensor, provided by the embodiment of the invention, the resistance training is carried out by combining the generator network and the discriminator network into the resistance network, so that the calculation capability of the generator network to the data is gradually improved, a better data conversion process can be realized under the condition of ensuring the implicit state characteristics of the data, and the virtual sensing function from the current and voltage data to the virtual vibration data of the generator network is realized.
Fig. 7 illustrates a physical schematic diagram of an electronic device, as shown in fig. 7, which may include: processor 710, communication interface (Communications Interface) 720, memory 730, and communication bus 740, wherein processor 710, communication interface 720, memory 730 communicate with each other via communication bus 740. Processor 710 may invoke logic instructions in memory 730 to perform a method of sensing vibration data based on a current-voltage sensor, the method comprising:
Acquiring current and voltage data acquired by a current and voltage sensor;
Inputting the current and voltage data into a generator network to obtain virtual vibration data;
The system comprises a generator network, a discriminator network, a first training set and a second training set, wherein the generator network and the discriminator network form an countermeasure network, and the countermeasure network is obtained by training a first training set through pre-collected current and voltage sample data, real vibration sample data corresponding to the current and voltage sample data and fault types corresponding to the current and voltage sample data.
Further, the logic instructions in the memory 730 described above may be implemented in the form of software functional units and may be stored in a computer readable storage medium when sold or used as a stand alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, embodiments of the present invention also provide a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the method for sensing vibration data based on a current-voltage sensor provided in the above method embodiments, the method comprising:
Acquiring current and voltage data acquired by a current and voltage sensor;
Inputting the current and voltage data into a generator network to obtain virtual vibration data;
The system comprises a generator network, a discriminator network, a first training set and a second training set, wherein the generator network and the discriminator network form an countermeasure network, and the countermeasure network is obtained by training a first training set through pre-collected current and voltage sample data, real vibration sample data corresponding to the current and voltage sample data and fault types corresponding to the current and voltage sample data.
In yet another aspect, embodiments of the present invention further provide a non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor, is implemented to perform the method for sensing vibration data based on a current-voltage sensor provided in the above embodiments, including:
Acquiring current and voltage data acquired by a current and voltage sensor;
Inputting the current and voltage data into a generator network to obtain virtual vibration data;
The system comprises a generator network, a discriminator network, a first training set and a second training set, wherein the generator network and the discriminator network form an countermeasure network, and the countermeasure network is obtained by training a first training set through pre-collected current and voltage sample data, real vibration sample data corresponding to the current and voltage sample data and fault types corresponding to the current and voltage sample data.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (9)
1. A method for sensing vibration data based on a current-voltage sensor, comprising:
Acquiring current and voltage data acquired by a current and voltage sensor;
Inputting the current and voltage data into a generator network to obtain virtual vibration data;
the system comprises a generator network, a discriminator network, a first training set and a second training set, wherein the generator network and the discriminator network form an countermeasure network, and the countermeasure network is obtained by training a first training set through pre-collected current and voltage sample data, real vibration sample data corresponding to the current and voltage sample data and fault types corresponding to the current and voltage sample data;
Specifically, the countermeasure network is trained by:
The current and voltage sample data and the real vibration sample data corresponding to the current and voltage sample data form a second training set to be input into the generator network so as to train the generator network;
Marking the vibration data output by the generator network as virtual vibration sample data, and inputting a third training set composed of the virtual vibration sample data, the real vibration sample data corresponding to the virtual vibration sample data and the fault type thereof into the discriminator network to train the discriminator network;
And forming the obtained generator network and the obtained discriminator network into an countermeasure network, and inputting the first training set into the countermeasure network to train the countermeasure network.
2. The method of sensing vibration data based on a current-voltage sensor of claim 1, wherein the generator network comprises: a downsampling layer, a data conversion layer and an upsampling layer;
inputting the current voltage data into a generator network to obtain virtual vibration data, comprising:
the downsampling layer receives input current and voltage data and generates first sampling data;
the data conversion layer receives the input first sampling data and generates first conversion data;
the up-sampling layer receives the input first conversion data and generates virtual vibration data.
3. The method of sensing vibration data based on a current-voltage sensor of claim 1, wherein the discriminator network comprises a first discriminator network and a second discriminator network;
The virtual vibration sample data, the real vibration sample data corresponding to the virtual vibration sample data and the fault type thereof form a third training set to be input into the discriminator network so as to train the discriminator network, and the method comprises the following steps:
inputting the virtual vibration sample data and the real vibration sample data to a first arbiter network to train the first arbiter network;
And inputting the virtual vibration sample data, the real vibration sample data and the fault type thereof into a second discriminator network to train the second discriminator network.
4. A method of sensing vibration data based on a current-voltage sensor according to claim 3, wherein the resulting generator network and arbiter network are formed into an countermeasure network, and wherein inputting the first training set into the countermeasure network to train the countermeasure network comprises:
Inputting the first training set into the countermeasure network, and alternately locking parameters of the discriminator network or the generator network to update the parameters of the generator network or the discriminator network so that a loss function of the countermeasure network is smaller than a first threshold, wherein the loss function of the countermeasure network is a combination of the loss functions of the first discriminator network and the second discriminator network.
5. A method of sensing vibration data based on a current-voltage sensor according to claim 3, wherein the first discriminator network is a convolutional neural network;
Inputting the virtual vibration sample data and the real vibration sample data to a first arbiter network to train the first arbiter network, comprising:
Inputting the virtual vibration sample data and the real vibration sample data into a first discriminator network to obtain the probability that the currently input data is the real vibration sample data;
and adjusting parameters of the first discriminator network so that the probability is greater than a second threshold when the input data is real vibration sample data.
6. A method of sensing vibration data based on a current-voltage sensor as claimed in claim 3, wherein the second discriminator network comprises: a first convolution layer, a time sequence data extraction layer, a second convolution layer and a normalization layer;
inputting the virtual vibration sample data, the real vibration sample data, and the fault type thereof to a second arbiter network to train the second arbiter network, comprising:
inputting the real vibration sample data and the virtual vibration sample data to the first convolution layer to generate first convolution data;
inputting the first convolution data to a time sequence data extraction layer to generate time sequence data;
inputting the time sequence data into the second convolution layer to generate second convolution data;
Inputting the second convolution data to a normalization layer to generate the prediction probability of the fault type of the real vibration sample data;
Inputting the fault type of the real vibration sample data, comparing the prediction probability with the fault type of the real vibration sample data, and counting the prediction accuracy of a second discriminator;
and adjusting parameters of the second discriminator network by taking the prediction accuracy larger than a third threshold as a target.
7. An apparatus for sensing vibration data based on a current-voltage sensor, comprising:
the acquisition module is used for acquiring current and voltage data acquired by the current and voltage sensor;
the sensing module is used for inputting the current and voltage data into the generator network so as to obtain virtual vibration data;
the system comprises a generator network, a discriminator network, a first training set and a second training set, wherein the generator network and the discriminator network form an countermeasure network, and the countermeasure network is obtained by training a first training set through pre-collected current and voltage sample data, real vibration sample data corresponding to the current and voltage sample data and fault types corresponding to the current and voltage sample data;
Specifically, the countermeasure network is trained by:
The current and voltage sample data and the real vibration sample data corresponding to the current and voltage sample data form a second training set to be input into the generator network so as to train the generator network;
Marking the vibration data output by the generator network as virtual vibration sample data, and inputting a third training set composed of the virtual vibration sample data, the real vibration sample data corresponding to the virtual vibration sample data and the fault type thereof into the discriminator network to train the discriminator network;
And forming the obtained generator network and the obtained discriminator network into an countermeasure network, and inputting the first training set into the countermeasure network to train the countermeasure network.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method of sensing vibration data based on a current-voltage sensor as claimed in any one of claims 1 to 6 when the program is executed.
9. A non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor, implements the steps of the method of sensing vibration data based on a current-voltage sensor according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011212653.8A CN112464990B (en) | 2020-11-03 | 2020-11-03 | Method and device for sensing vibration data based on current-voltage sensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011212653.8A CN112464990B (en) | 2020-11-03 | 2020-11-03 | Method and device for sensing vibration data based on current-voltage sensor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112464990A CN112464990A (en) | 2021-03-09 |
| CN112464990B true CN112464990B (en) | 2024-05-10 |
Family
ID=74835878
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011212653.8A Active CN112464990B (en) | 2020-11-03 | 2020-11-03 | Method and device for sensing vibration data based on current-voltage sensor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112464990B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113552450A (en) * | 2021-07-07 | 2021-10-26 | 上海交通大学 | Partial discharge source positioning method based on virtual sensor |
| CN113946920A (en) * | 2021-10-22 | 2022-01-18 | 大连海事大学 | Rolling bearing fault diagnosis method with unbalanced data and data set deviation |
| CN116087814B (en) * | 2023-01-28 | 2023-11-10 | 上海玫克生储能科技有限公司 | Method and device for improving voltage sampling precision and electronic equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110414601A (en) * | 2019-07-30 | 2019-11-05 | 南京工业大学 | Photovoltaic module fault diagnosis method, system and equipment based on deep convolution countermeasure network |
| WO2020038548A1 (en) * | 2018-08-20 | 2020-02-27 | Telefonaktiebolaget Lm Ericsson (Publ) | Improving immune system of sites using generative adversarial networks and reinforcement learning |
-
2020
- 2020-11-03 CN CN202011212653.8A patent/CN112464990B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020038548A1 (en) * | 2018-08-20 | 2020-02-27 | Telefonaktiebolaget Lm Ericsson (Publ) | Improving immune system of sites using generative adversarial networks and reinforcement learning |
| CN110414601A (en) * | 2019-07-30 | 2019-11-05 | 南京工业大学 | Photovoltaic module fault diagnosis method, system and equipment based on deep convolution countermeasure network |
Non-Patent Citations (1)
| Title |
|---|
| 基于生成式对抗网络的窃电检测数据生成方法;王德文;杨凯华;;电网技术(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112464990A (en) | 2021-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112464990B (en) | Method and device for sensing vibration data based on current-voltage sensor | |
| Oh et al. | Scalable and unsupervised feature engineering using vibration-imaging and deep learning for rotor system diagnosis | |
| CN110288004B (en) | System fault diagnosis method and device based on log semantic mining | |
| CN110207997B (en) | Liquid rocket engine fault detection method based on convolution self-encoder | |
| Gao et al. | ASM1D-GAN: An intelligent fault diagnosis method based on assembled 1D convolutional neural network and generative adversarial networks | |
| Ghimire et al. | A rough set-theory-based fault-diagnosis method for an electric power-steering system | |
| CN105224872A (en) | A kind of user's anomaly detection method based on neural network clustering | |
| CN110324337B (en) | Vehicle intranet intrusion detection method and system based on capsule neural network | |
| CN112380767B (en) | Equipment fault diagnosis method and system based on improved generation countermeasure network | |
| CN114760098A (en) | CNN-GRU-based power grid false data injection detection method and device | |
| Plakias et al. | A novel information processing method based on an ensemble of Auto-Encoders for unsupervised fault detection | |
| CN106384092A (en) | Online low-rank abnormal video event detection method for monitoring scene | |
| CN112200114A (en) | Fault diagnosis model training method and device, electronic equipment and storage medium | |
| CN113259207B (en) | QRNN-based stateful network protocol fuzzy test case filtering method | |
| CN114048468A (en) | Intrusion detection method, intrusion detection model training method, device and medium | |
| CN110503113A (en) | A kind of saliency object detection method restored based on low-rank matrix | |
| CN113537284A (en) | Deep learning implementation method and system based on mimicry mechanism | |
| CN115114965A (en) | Wind turbine generator gearbox fault diagnosis model, method, equipment and storage medium | |
| CN115792615A (en) | Fault diagnosis method and system for permanent magnet synchronous motor sensor | |
| CN110263836B (en) | Bad driving state identification method based on multi-feature convolutional neural network | |
| CN116443031B (en) | Wheel speed processing system and method of vehicle body electronic stability control system | |
| CN115618263A (en) | Feature-level SMOTE-based complex equipment unbalance fault diagnosis method | |
| CN115099264A (en) | Ship part fault diagnosis method and device, computer and computer storage medium | |
| de Oliveira et al. | Fault Detection and Isolation in Inertial Measurement Units Based on χ2‐CUSUM and Wavelet Packet | |
| CN111967364B (en) | Composite fault diagnosis method, device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |